mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 21:51:28 +00:00
[CK_TILE] Tile loop persistent gemm kernel (#2191)
* Implement tile loop persistent gemm kernel * Enable timing * Add tests for persistent gemm * Fix formatting * Fix gemm_basic * Rename True/False to Persistent/NonPersistent * Use only one set of layouts for persistent tests * Fix gemm example persistent template parameter * Fix formatting
This commit is contained in:
@@ -213,7 +213,8 @@ auto create_args(int argc, char* argv[])
|
||||
.insert("repeat", "100", "number of iterations to benchmark the kernel")
|
||||
.insert("timer", "gpu", "gpu:gpu timer, cpu:cpu timer")
|
||||
.insert("split_k", "1", "splitK value")
|
||||
.insert("init", "0", "0:random, 1:linear, 2:constant(1)");
|
||||
.insert("init", "0", "0:random, 1:linear, 2:constant(1)")
|
||||
.insert("persistent", "0", "0:non-persistent, 1:persistent");
|
||||
|
||||
bool result = arg_parser.parse(argc, argv);
|
||||
return std::make_tuple(result, arg_parser);
|
||||
@@ -226,5 +227,6 @@ template <typename ADataType,
|
||||
typename CDataType,
|
||||
typename ALayout,
|
||||
typename BLayout,
|
||||
typename CLayout>
|
||||
typename CLayout,
|
||||
bool Persistent = false>
|
||||
float gemm_calc(const ck_tile::GemmHostArgs& args, const ck_tile::stream_config& s);
|
||||
|
||||
Reference in New Issue
Block a user